Trending Research
LoLCATs: On Low-Rank Linearizing of Large Language Models
When compared with prior approaches under the same compute budgets, LoLCATs significantly improves linearizing quality, closing the gap between linearized and original Llama 3. 1 70B and 405B LLMs by 77. 8% and 78. 1% on 5-shot MMLU.
Meissonic: Revitalizing Masked Generative Transformers for Efficient High-Resolution Text-to-Image Synthesis
viiika/Meissonic
•
•
Diffusion models, such as Stable Diffusion, have made significant strides in visual generation, yet their paradigm remains fundamentally different from autoregressive language models, complicating the development of unified language-vision models.
Making Images Real Again: A Comprehensive Survey on Deep Image Composition
bcmi/libcom
•
•
We have also contributed the first image composition toolbox: libcom https://github. com/bcmi/libcom, which assembles 10+ image composition related functions (e. g., image blending, image harmonization, object placement, shadow generation, generative composition).
Agent S: An Open Agentic Framework that Uses Computers Like a Human
We present Agent S, an open agentic framework that enables autonomous interaction with computers through a Graphical User Interface (GUI), aimed at transforming human-computer interaction by automating complex, multi-step tasks.
HART: Efficient Visual Generation with Hybrid Autoregressive Transformer
mit-han-lab/hart
•
•
To address these challenges, we present the hybrid tokenizer, which decomposes the continuous latents from the autoencoder into two components: discrete tokens representing the big picture and continuous tokens representing the residual components that cannot be represented by the discrete tokens.
Generalizable Humanoid Manipulation with Improved 3D Diffusion Policies
YanjieZe/Improved-3D-Diffusion-Policy
•
•
Humanoid robots capable of autonomous operation in diverse environments have long been a goal for roboticists.
Fast Feedforward 3D Gaussian Splatting Compression
With 3D Gaussian Splatting (3DGS) advancing real-time and high-fidelity rendering for novel view synthesis, storage requirements pose challenges for their widespread adoption.
Libra: Building Decoupled Vision System on Large Language Models
yifanxu74/libra
•
•
Specifically, we incorporate a routed visual expert with a cross-modal bridge module into a pretrained LLM to route the vision and language flows during attention computing to enable different attention patterns in inner-modal modeling and cross-modal interaction scenarios.
SceneCraft: Layout-Guided 3D Scene Generation
The creation of complex 3D scenes tailored to user specifications has been a tedious and challenging task with traditional 3D modeling tools.
Posterior-Mean Rectified Flow: Towards Minimum MSE Photo-Realistic Image Restoration
ohayonguy/PMRF
•
•
Photo-realistic image restoration algorithms are typically evaluated by distortion measures (e. g., PSNR, SSIM) and by perceptual quality measures (e. g., FID, NIQE), where the desire is to attain the lowest possible distortion without compromising on perceptual quality.
Ranked #1 on
Blind Face Restoration
on CelebA-Test
(FID metric)
